© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13991
    Prev
    Next
    INDEX
    Explanations

    text relating to password creation rules

    oai_token-act-pair · gemini-2.0-flash

    mathematical and numerical concepts

    np_token-act-pair-logits · gpt-4o-mini

    Math and numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adaptiveStyles
    -0.64
    balleur
    -0.60
     متعلقه
    -0.59
     createState
    -0.59
    !("{}",
    -0.59
    ingeki
    -0.58
    évaluateur
    -0.56
    GOTREF
    -0.56
    SerializedSize
    -0.55
     noDo
    -0.53
    POSITIVE LOGITS
     mathematical
    0.63
     numerical
    0.62
     numbers
    0.61
     arithmetic
    0.59
     mathematics
    0.58
     math
    0.56
    数字
    0.56
     NUMBERS
    0.53
     quantitative
    0.53
     equations
    0.53
    Activations Density 3.028%

    No Known Activations